Penentuan Kematangan Buah Salak Pondoh Di Pohon Berbasis Pengolahan Citra Digital
Abstract: Because there is no
a system based on Digital Image Processing to determine the degree of ripeness
of Salak Pondoh (Salacca zalacca Gaertner Voss.) on tree, then this study has
attempted to implement such a system. System was built with consists of several
sub-processes. First, the segmentation process, the system will perform a
search of pixels alleged pixels salak pondoh, by utilizing the features of
color components r, g, b, and gray of each pixel salak pondoh then calculated
large the dissimilarity ( Euclidean Distance ) against values of data
features , ,
, and comparison. If the value of dissimilarity
less than the threshold value and is also supported by the neighboring pixels
from different directions has a value of dissimilarity is less than a threshold value, the pixel is
set as an object pixel, for the other condition set as background pixels. For
the next, improvements through an elimination noise stage and filling in the
pixels to get a perfect binary image segmentation. Second, classification, by knowning the mean
value of R and V of the entire pixel object, then the level of ripeness salak pondoh
can be determined by using the method of classification backpropagation or k
-Nearest Neighbor. From the test results indicate that the success of the
system by 92% when using a backpropagatioan classification algorithm and 93%
with k-Nearest Neighbor algorithm.
Penulis: Pawit Rianto
Kode Jurnal: jptinformatikadd170069
